\name{featureCTD} \alias{featureCTD} \title{Feature Coding by composition, transition and distribution} \description{ Sequences are coded based on their composition, transition and distribution. } \usage{ featureCTD(seq,class=elements("aminoacid")) } \arguments{ \item{seq}{a string vector for the protein, DNA, or RNA sequences.} \item{class}{a list for the class of biological properties. It can be produced by \code{\link{elements}} and \code{\link{aaClass}}.} } \details{ \code{\link{featureCTD}} returns a matrix with M+M*(M-1)/2+M*5 columns. Each row represented features of one sequence coding by a M+M*(M-1)/2+M*5 dimension numeric vector. Three kinds of coding: composition (C), transition (T) and distribution (D) are used. C is the number of amino acids of a particular property (such as hydrophobicity) divided by the total number of amino acids. T characterizes the percent frequency with which amino acids of a particular property is followed by amino acids of a different property. D measures the chain length within which the first, 25, 50, 75 and 100% of the amino acids of a particular property is located respectively. } \author{Hong Li} \examples{ if(interactive()){ file = file.path(.path.package("BioSeqClass"), "example", "acetylation_K.fasta") library(Biostrings) tmp = readFASTA(file) proteinSeq = sapply(tmp,function(x){x[["seq"]]}) names(proteinSeq) = sapply(tmp,function(x){x[["desc"]]}) CTD1 = featureCTD(proteinSeq, class=elements("aminoacid") ) CTD2 = featureCTD(proteinSeq, class=aaClass("aaV") ) } }